Afbudsrejser travel search

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the operation as read-only and non-destructive. The description adds context beyond annotations by revealing this is an NDC-based API with charter-flight inventory not available on mainstream OTAs, which helps set expectations about result uniqueness and source.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, with the core scope in the first sentence and valuable data-source context in the second. The final sentence is somewhat redundant with the first but the overall description remains tight and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 17 optional parameters and no output schema, the description does not explain parameter interactions (e.g., exact dates vs. date ranges) or what the response structure looks like. It is adequate for basic selection but leaves important invocation details to inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with all 17 parameters already documented with defaults, formats, examples, and NDC mappings. The description adds no additional parameter-level meaning beyond the generic 'based on search criteria,' so the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource ('søge efter flyrejser') and explicitly scopes it to flights from Denmark. The phrase 'kun fly' separates it from the sibling search_holidays, and the charter-flight inventory detail further defines what kind of offers are returned.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly signals this tool is for flight-only searches from Denmark, which implies the alternative search_holidays covers broader holiday packages. However, it does not explicitly name the sibling or state conditions like 'use this when the user wants flights only and search_holidays when they want packages.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, covering the safety profile. The description adds useful market context (largest Danish database, multiple tour operators) but no operational behavior such as default limit, sort order, or response shape. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, under 60 words, and communicates purpose, scope, and data sources efficiently. There is minor redundancy ('bedste' and 'pakkerejse' appear twice), but nothing that materially hurts clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only search tool with fully schema-documented optional filters and annotations covering safety, the description is largely sufficient. 'Find de bedste tilgængelige pakkerejser fra Danmark' implies the returned resource, and the fields parameter documents output options. The main omission is explicit routing away from search_flights.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and all 37 parameters include descriptions, examples, defaults, and enums. The description adds no parameter-level meaning, but the schema already carries the full burden, justifying the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action—search ('søge')—over a package-holiday database from Denmark, and it names the resource domain ('pakkerejsetilbud') and suppliers. It does not explicitly differentiate from the sibling search_flights; the distinction rests on 'pakkerejser' versus flights rather than an explicit contrast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrases 'API'et bruges til at give de bedste tilbud på pakkerejser' and 'Find de bedste tilgængelige pakkerejser fra Danmark' imply the tool is for package-holiday searches. However, there is no explicit when-to-use versus when-not-to-use guidance, and the sibling search_flights is never mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.